© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96233
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StackNavigator
    -0.74
     pinulongan
    -0.71
    principalTable
    -0.69
     nakalista
    -0.59
    ようになります
    -0.57
    WithIOException
    -0.56
     everything
    -0.55
    就把
    -0.54
     stanga
    -0.53
     lenker
    -0.52
    POSITIVE LOGITS
    DoubleQuotes
    0.57
    brainly
    0.54
    <bos>
    0.47
    TAWA
    0.45
    DebuggerStep
    0.45
    Hentet
    0.45
     heapq
    0.45
     <=",
    0.45
    Gön
    0.45
    yourself
    0.44
    Activations Density 0.012%

    No Known Activations